Xinmei Tian

27

Papers

13

Total Citations

Papers (27)

Robust Training of Federated Models with Extremely Label Deficiency

A Similarity Paradigm Through Textual Regularization Without Forgetting

Detecting Generated Images by Fitting Natural Image Distributions

Towards Theoretical Understandings of Self-Consuming Generative Models

Interpreting and Improving Large Language Models in Arithmetic Calculation

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning

A Twofold Siamese Network for Real-Time Object Tracking

Gaussian Temporal Awareness Networks for Action Localization

Camera Lens Super-Resolution

Compact Feature Learning for Multi-Domain Image Classification

Quantization Networks

Learning Spatio-Temporal Representation With Local and Global Diffusion

Revisiting Knowledge Distillation: An Inheritance and Exploration Framework

Prompt Distribution Learning

Meta Convolutional Neural Networks for Single Domain Generalization

Learning To Collaborate in Decentralized Learning of Personalized Models

A Style and Semantic Memory Mechanism for Domain Generalization

3D Local Convolutional Neural Networks for Gait Recognition

Learning to Localize Actions from Moments

Self-Supervision Can Be a Good Few-Shot Learner

Exploring Object Relation in Mean Teacher for Cross-Domain Detection

Sheared Backpropagation for Fine-tuning Foundation Models

Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning

Class-Disentanglement and Applications in Adversarial Detection and Defense

Towards Lightweight Black-Box Attack Against Deep Neural Networks

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach

FedFed: Feature Distillation against Data Heterogeneity in Federated Learning